Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    **Subject: or *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;(
    0.39
    邂
    0.39
     cet
    0.35
     cab
    0.34
    ष्णा
    0.34
     stek
    0.33
     motivos
    0.33
     unidades
    0.32
    काब
    0.32
     oct
    0.32
    POSITIVE LOGITS
    តម្លៃ
    0.44
    🩷
    0.44
     වැඩි
    0.41
    禧
    0.41
    🟢
    0.41
    🕒
    0.41
    secretary
    0.41
    更
    0.41
    ลูก
    0.40
    టువంటి
    0.40
    Act Density 0.000%

    No Known Activations